The central role of density functional theory in the AI age

Autor(en)

Bing Huang, Guido Falk von Rudorff, O. Anatole von Lilienfeld

Abstrakt

Density functional theory (DFT) plays a pivotal role in chemical and materials science because of its relatively high predictive power, applicability, versatility, and computational efficiency. We review recent progress in machine learning (ML) model developments, which have relied heavily on DFT for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in a broader context for chemical and materials sciences. DFT-based ML models have reached high efficiency, accuracy, scalability, and transferability and pave the way to the routine use of successful experimental planning software within self-driving laboratories.

Organisation(en)

Computergestützte Materialphysik

Externe Organisation(en)

Universität Kassel, Vector Institute for Artificial Intelligence, University of Toronto, Technische Universität Berlin

Journal

Science

Band

381

Seiten

170-175

Anzahl der Seiten

6

ISSN

0036-8075

DOI

https://doi.org/10.1126/science.abn3445

Publikationsdatum

07-2023

Peer-reviewed

Ja

ÖFOS 2012

103006 Chemische Physik, 102019 Machine Learning

ASJC Scopus Sachgebiete

General

Link zum Portal

https://ucrisportal.univie.ac.at/de/publications/197ca089-8a78-4bd6-9478-0fc307153f5b